© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 2-GEMMASCOPE-2-TRANSCODER-16K
    7. 1196
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/transcoder_all/layer_2_width_16k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ة
    2.83
    e
    2.77
    <bos>
    2.43
    日閲覧
    2.43
     dalle
    2.36
    я
    2.24
    য়
    2.17
     কেবল
    2.14
     unge
    2.14
     sempat
    2.12
    POSITIVE LOGITS
     itching
    2.68
    sht
    2.67
     monolayers
    2.61
    localObject
    2.55
    ر
    2.54
    و
    2.38
     procuring
    2.34
    悱
    2.33
     основании
    2.31
    okhlov
    2.30
    Activations Density 0.004%

    No Known Activations